AI Intelligence

• Context-Aware: Remembers conversation history and dataset details
• Smart Responses: Detailed explanations of data patterns
• Query Suggestions: Intelligent recommendations for data exploration
• Error Handling: Graceful fallbacks and helpful error messages

Modern UI/UX

• Responsive Design: Mobile-first approach, works on all devices
• Dark Theme: Easy on the eyes with neon accents
• Smooth Animations: Framer Motion transitions and feedback
• Accessibility: Voice control and keyboard navigation

🚀 Quick Start

Prerequisites

• Node.js 18+
• Python 3.11+
• Gemini API Key

📸 Application Screenshots

Main Dashboard Interface

Data Analysis View

Statistical Insights

Correlation Matrix

Voice Interaction Interface

Data Quality Overview

Chart Visualization

Sample Dataset Explorer

Local Development Setup

1. Clone & Install

   git clone https://github.com/charan22640/voice-ai-data-analyst.git
   cd voice-ai-data-analyst
   

2. Backend Setup

   cd backend
   python -m venv venv
   source venv/bin/activate  # Windows: venv\\Scripts\\activate
   pip install -r requirements.txt
   

   Create backend/.env:

   GEMINI_API_KEY=your_key_here
   FLASK_DEBUG=True
   PORT=5000
   

3. Frontend Setup

   cd frontend
   npm install
   

   Create frontend/.env if needed:

   VITE_API_URL=http://localhost:5000
   

4. Run Development Servers

   # Terminal 1 (Backend)
   cd backend
   python app.py
   
   # Terminal 2 (Frontend)
   cd frontend
   npm run dev
   

Docker Setup

# Add API key to backend/.env first
echo "GEMINI_API_KEY=your_key_here" > backend/.env

# Build and run
docker-compose up --build

📖 Usage Guide

Voice Interaction

1. Click the microphone button or press Space to start voice input
2. Speak naturally (e.g., "Analyze the sales trends")
3. Get AI responses with optional voice playback

Data Analysis

1. Upload CSV/Excel or select a sample dataset
2. Ask questions like:
   • "What's the average revenue by region?"
   • "Show correlations between price and quantity"
   • "Are there any outliers in the sales data?"
3. Explore auto-generated visualizations and insights

Chat Features

• Context-Aware: References previous conversations
• Data-Aware: Understands current dataset details
• Multi-Modal: Switch between voice and text seamlessly
• Rich Responses: Text, charts, and voice synthesis

🏗️ Project Structure

nova-assistant/
├── backend/
│   ├── app.py              # Flask application entry
│   ├── routes/
│   │   ├── ai.py          # AI & TTS endpoints
│   │   └── data.py        # Data analysis endpoints
│   ├── services/
│   │   ├── gemini_service.py
│   │   ├── data_service.py
│   │   └── tts_service.py
│   └── requirements.txt
├── frontend/
│   ├── src/
│   │   ├── components/    # React components
│   │   ├── hooks/        # Custom React hooks
│   │   └── App.jsx
│   └── package.json
└── docker-compose.yml

🔧 API Documentation

AI Endpoints

POST /api/ai/chat           # Conversational AI with context
POST /api/ai/tts           # Text-to-speech generation
GET  /api/ai/status        # Service health check

Data Endpoints

POST /api/data/upload      # Upload & analyze data files
POST /api/data/query       # Natural language queries
GET  /api/data/info        # Dataset information
GET  /api/data/insights    # Automated insights

⚙️ Configuration

Backend (.env)

GEMINI_API_KEY=your_key_here  # Required: Get from Google AI
FLASK_DEBUG=False             # Set True for development
PORT=5000                     # API server port
CORS_ORIGINS=http://localhost:3000  # Frontend URL(s)

Frontend (.env)

VITE_API_URL=http://localhost:5000  # Backend API URL

❗ Troubleshooting

• 500 Chat Error: Fixed by improving DataService with public helpers
• Message Truncation: Resolved Gemini stopSequences issue with bold text
• Sample Data: Frontend now properly handles upload responses
• React Keys: Using crypto.randomUUID() for unique message IDs
• Missing Libraries: Ensure venv is active and all deps installed
• CORS Issues: Check CORS_ORIGINS matches frontend URL

🔒 Security Notes

• Keep GEMINI_API_KEY on backend only - never expose to browser
• Clean up uploaded files from backend/static/ when not needed
• Use HTTPS in production for secure data transmission

🙌 Contributing

1. Fork the repository
2. Create feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'feat: add amazing feature'
4. Push to branch: git push origin feature/amazing-feature
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Google AI - Gemini AI API
• React - Frontend framework
• Flask - Backend framework
• Tailwind CSS - Styling
• Framer Motion - Animations

⭐ Star this repo if you found it helpful!